EP2566144B1 - Transcription de conférence de voix sur texte - Google Patents
Transcription de conférence de voix sur texte Download PDFInfo
- Publication number
- EP2566144B1 EP2566144B1 EP11179790.8A EP11179790A EP2566144B1 EP 2566144 B1 EP2566144 B1 EP 2566144B1 EP 11179790 A EP11179790 A EP 11179790A EP 2566144 B1 EP2566144 B1 EP 2566144B1
- Authority
- EP
- European Patent Office
- Prior art keywords
- transcript
- conference
- partial
- transcripts
- speech
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000013518 transcription Methods 0.000 title claims description 129
- 230000035897 transcription Effects 0.000 title claims description 129
- 238000004891 communication Methods 0.000 claims description 60
- 238000000034 method Methods 0.000 claims description 32
- 238000005304 joining Methods 0.000 claims description 3
- 230000004931 aggregating effect Effects 0.000 claims 1
- 238000013500 data storage Methods 0.000 description 18
- 238000006243 chemical reaction Methods 0.000 description 12
- 230000002085 persistent effect Effects 0.000 description 12
- 238000009826 distribution Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 10
- 230000005540 biological transmission Effects 0.000 description 7
- 230000009471 action Effects 0.000 description 6
- 230000001413 cellular effect Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000013519 translation Methods 0.000 description 5
- 230000003190 augmentative effect Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000004044 response Effects 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 230000010267 cellular communication Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 230000011664 signaling Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/56—Arrangements for connecting several subscribers to a common circuit, i.e. affording conference facilities
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M2201/00—Electronic components, circuits, software, systems or apparatus used in telephone systems
- H04M2201/40—Electronic components, circuits, software, systems or apparatus used in telephone systems using speech recognition
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M2250/00—Details of telephonic subscriber devices
- H04M2250/62—Details of telephonic subscriber devices user interface aspects of conference calls
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/56—Arrangements for connecting several subscribers to a common circuit, i.e. affording conference facilities
- H04M3/562—Arrangements for connecting several subscribers to a common circuit, i.e. affording conference facilities where the conference facilities are distributed
Definitions
- Example embodiments relate to transcription systems and methods, and in particular to a method for transcribing conference calls.
- one method for automating note taking is simply to provide an audio recording to the conference call.
- some, if not most, of the information provided is not needed by all the conference participants, thus, creating a large audio transcript of the conference that is largely useless to many of the conference participants.
- the entire conference call is transcribed to a purely textual transcript. But pure text sometimes does not reflect the nuances of speech that can change the intended meaning of the text. Additionally, the size of the transcript can become quite large if one is created for the entire conference.
- US 6,850,609 B1 describes a method and an apparatus for providing recording and/or transcription services, e.g, as part of a communication system, wherein the recording and/or transcription device is remote from one or more audio sources, e.g., telephones.
- US 2009/326939 A1 relates to a system and method to use a telephone, such as a voice over Internet Protocol (VoIP) phone, and more particularly, to a system that is configured to provide speech to text capabilities. Therein, speech is converted to text during a telephone call and the text is displayed for a party on the telephone call.
- VoIP voice over Internet Protocol
- EP 1798 945 A1 discloses a speech to text transcription system which is resident on a "WIS U-MGR(33) ('Who is Speaking' Use Manager)" located at a WAN-based computer station.
- the example embodiments provided below describe a transcription device, computer readable medium, and method for joining an audio conference call with a device associated with a participant, of a plurality of participants joined to the conference through one or more associated devices.
- the method creates a speech audio file corresponding to a portion of the participant's speech during the conference and converts contemporaneously, at the device, the speech audio file to a local partial transcript. Additionally, the method acquires a plurality of partial transcripts from at least one of the associated devices, so that the device can provide a complete transcript.
- Types of transcripts can include partial, complete, audio, text, linked, or any combination thereof.
- a partial transcript can embody a particular transcribed segment of the conference that corresponds to a particular user. When the partial transcripts from all conference participants are collected and arranged in chronological order, a complete transcript is created. In a linked transcript, portions of the text are mapped to the corresponding recorded audio, such that a user can read the text of the transcript or listen to the corresponding audio recording from which the text was created.
- System 100 includes an enterprise network 105, which in some embodiments includes a local area network (LAN).
- enterprise network 105 can be an enterprise or business system.
- enterprise network 105 includes more than one network and is located in multiple geographic areas.
- Enterprise network 105 is coupled, often through a firewall 110, to a wide area network (WAN) 115, such as the Internet.
- Enterprise network 105 can also be coupled to a public switched telephone network (PSTN) 128 via direct inward dialing (DID) trunks or primary rate interface (PRI) trunks (not shown).
- PSTN public switched telephone network
- DID direct inward dialing
- PRI primary rate interface
- Enterprise network 105 can also communicate with a public land mobile network (PLMN) 120, which is also referred to as a wireless wide area network (WWAN) or, in some cases, a cellular network.
- PLMN public land mobile network
- WWAN wireless wide area network
- the connection with PLMN 120 is via a relay 125.
- enterprise network 105 provides a wireless local area network (WLAN), not shown, featuring wireless access points, such as wireless access point 125a.
- WLAN wireless local area network
- other WLANs can exist outside enterprise network 105.
- a WLAN coupled to WAN 115 can be accessed via wireless access point 125b.
- WAN 115 is coupled to one or more mobile devices, for example mobile device 140. Additionally, WAN 115 can be coupled to one or more desktop or laptop computers 142 (one shown in Figure 1 ).
- System 100 can include a number of enterprise-associated mobile devices, for example, mobile devices 130, 135, 136, and 140.
- Mobile devices 130, 135, 136, and 140 can include devices equipped for cellular communication through PLMN 120, mobile devices equipped for Wi-Fi communications over one of the WLANs via wireless access points 125a or 125b, or dual-mode devices capable of both cellular arid WLAN communications.
- Wireless access points 125a or 125b can be configured to WLANs that operate in accordance with one of the IEEE 802.11 specifications.
- Mobile devices 130, 135, 136, and 140 can be, for example, cellular phones, smartphones, tablets, netbooks, and PDAs (personal digital assistants) enabled for wireless communication. Moreover, mobile devices 130, 135, 136, and 140 can communicate with other components using voice communications or data communications (such as accessing content from a website). Mobile devices 130, 135, 136, and 140 include devices equipped for cellular communication through PLMN 120, devices equipped for Wi-Fi communications via wireless access points 125a or 125b, or dual-mode devices capable of both cellular and WLAN communications. Mobile devices 130, 135, 136, and 140 are described in more detail below in Figure 2 .
- Mobile devices 130,135,136, and 140 also include one or more radio transceivers and associated processing hardware and software to enable wireless communications with PLMN 120, and/or one of the WLANs via wireless access points 125a or 125b.
- PLMN 120 and mobile devices 130,135, 136, and 140 are configured to operate in compliance with any one or more of a number of wireless protocols, including GSM, GPRS, CDMA, EDGE, UMTS, EvDO, HSPA, 3GPP, or a variety of others. It will be appreciated that mobile devices 130, 135, 136, and 140 can roam within PLMN 120 and across PLMNs, in known manner, as their user moves.
- dual-mode mobile devices 130, 135, 136, and 140 and/or enterprise network 105 are configured to facilitate roaming between PLMN 120 and a wireless access points 125a or 125b, and are thus capable of seamlessly transferring sessions (such as voice calls) from a connection with the cellular interface of dual-mode device 130,135,136, and 140 to a WLAN interface of the dual-mode device, and vice versa.
- Enterprise network 105 typically includes a number of networked servers, computers, and other devices.
- enterprise network 105 can connect one or more desktop or laptop computers 143 (one shown). The connection can be wired or wireless in some embodiments.
- Enterprise network 105 can also connect to one or more digital telephone phones 160.
- Relay 125 serves to route messages received over PLMN 120 from mobile device 130 to corresponding enterprise network 105. Relay 125 also pushes messages from enterprise network 105 to mobile device 130 via PLMN 120.
- Enterprise network 105 also includes an enterprise server 150. Together with relay 125, enterprise server 150 functions to redirect or relay incoming e-mail messages addressed to a user's e-mail address through enterprise network 105 to mobile device 130 and to relay incoming e-mail messages composed and sent via mobile device 130 out to the intended recipients within WAN 115 or elsewhere. Enterprise server 150 and relay 125 together facilitate a "push" e-mail service for mobile device 130, enabling the user to send and receive e-mail messages using mobile device 130 as though the user were coupled to an e-mail client within enterprise network 105 using the user's enterprise-related e-mail address, for example on computer 143.
- enterprise network 105 includes a Private Branch eXchange (although in various embodiments the PBX can be a standard PBX or an IP-PBX, for simplicity the description below uses the term PBX to refer to both) 127 having a connection with PSTN 128 for routing incoming and outgoing voice calls for the enterprise.
- PBX 127 is coupled to PSTN 128 via DID trunks or PRI trunks, for example.
- PBX 127 can use ISDN signaling protocols for setting up and tearing down circuit-switched connections through PSTN 128 and related signaling and communications.
- PBX 127 can be coupled to one or more conventional analog telephones 129.
- PBX 127 is also coupled to enterprise network 105 and, through it, to telephone terminal devices, such as digital telephone sets 160, softphones operating on computers 143, etc.
- each individual can have an associated extension number, sometimes referred to as a PNP (private numbering plan), or direct dial phone number.
- Calls outgoing from PBX 127 to PSTN 128 or incoming from PSTN 128 to PBX 127 are typically circuit-switched calls.
- voice calls are often packet-switched calls, for example Voice-over-IP (VoIP) calls.
- VoIP Voice-over-IP
- the System 100 includes one or more conference bridges 132.
- the conference bridge 132 can be part of the enterprise network 105. Additionally, in some embodiments, the conference bridge 132 can be accessed via WAN 115 or PTSN 128.
- Enterprise network 105 can further include a Service Management Platform (SMP) 165 for performing some aspects of messaging or session control, like call control and advanced call processing features.
- Service Management Platform (SMP) can have one or more processors and at least one memory for storing program instructions.
- the processor(s) can be a single or multiple microprocessors, field programmable gate arrays (FPGAs), or digital signal processors (DSPs) capable of executing particular sets of instructions.
- Computer-readable instructions can be stored on a tangible non-transitory computer-readable medium, such as a flexible disk, a hard disk, a CD-ROM (compact disk-read only memory), and MO (magneto-optical), a DVD-ROM (digital versatile disk-read only memory), a DVD RAM (digital versatile disk-random access memory), or a semiconductor memory.
- a tangible non-transitory computer-readable medium such as a flexible disk, a hard disk, a CD-ROM (compact disk-read only memory), and MO (magneto-optical), a DVD-ROM (digital versatile disk-read only memory), a DVD RAM (digital versatile disk-random access memory), or a semiconductor memory.
- the methods can be implemented in hardware components or combinations of hardware and software such as, for example, ASICs, special purpose computers, or general purpose computers.
- SMP 165 can be configured to group a plurality of received partial transcripts by conference, assemble the grouped partial transcripts in chronological order to create a complete transcript
- SMP 165 Collectively SMP 165, conference bridge 132, and PBX 127 are referred to as the enterprise communications platform 180. It will be appreciated that enterprise communications platform 180 and, in particular, SMP 165, is implemented on one or more servers having suitable communications interfaces for connecting to and communicating with PBX 127, conference bridge 132, and DID/PRI trunks. Although SMP 165 can be implemented on a stand-alone server, it will be appreciated that it can be implemented into an existing control agent/server as a logical software component.
- Mobile device 130 has a transcription system 300 and is in communication with enterprise network 105.
- Transcription system 300 can include one or more processors (not shown), a memory (not shown).
- the processor(s) can be a single or multiple microprocessors, field programmable gate arrays (FPGAs), or digital signal processors (DSPs) capable of executing particular sets of instructions.
- Computer-readable instructions can be stored on a tangible non-transitory computer-readable medium, such as a flexible disk, a hard disk, a CD-ROM (compact disk-read only memory), and MO (magneto-optical), a DVD-ROM (digital versatile disk-read only memory), a DVD RAM (digital versatile disk-random access memory), or a semiconductor memory.
- Transcription system 300 can be implemented on a mobile device, a computer (for example, computer 142 or computer 132), a digital phone 160, distributed across a plurality of computers, or some combination thereof.
- transcription system 300 can be distributed across mobile devices 130, 135, 136, and 140 and SMP 165.
- Mobile device 130 is a two-way communication device having data and voice communication capabilities, and the capability to communicate with other computer systems, for example, via the Internet.
- mobile device 130 can be a handheld device, a multiple-mode communication device configured for both data and voice communication, a smartphone, a mobile telephone, a netbook, a gaming console, a tablet, or a PDA (personal digital assistant) enabled for wireless communication.
- PDA personal digital assistant
- Mobile device 130 includes a rigid case (not shown) housing the components of mobile device 130.
- the internal components of mobile device 130 can, for example, be constructed on a printed circuit board (PCB).
- PCB printed circuit board
- Mobile device 130 includes a controller comprising at least one processor 240 (such as a microprocessor), which controls the overall operation of mobile device 130.
- Processor 240 interacts with device subsystems such as a communication systems 211 for exchanging radio frequency signals with the wireless network (for example WAN 115 and/or PLMN 120) to perform communication functions.
- device subsystems such as a communication systems 211 for exchanging radio frequency signals with the wireless network (for example WAN 115 and/or PLMN 120) to perform communication functions.
- the wireless network for example WAN 115 and/or PLMN 120
- Processor 240 interacts with additional device subsystems including a display 204 such as a liquid crystal display (LCD) screen or any other appropriate display, input devices 206 such as a keyboard and control buttons, persistent memory 244, random access memory (RAM) 246, read only memory (ROM) 248, auxiliary input/output (I/O) subsystems 250, data port 252 such as a conventional serial data port or a Universal Serial Bus (USB) data port, speaker 256, microphone 258, short-range communication subsystem 262 (which can employ any appropriate wireless (for example, RF), optical, or other short range communications technology), and other device subsystems generally designated as 264.
- a display 204 such as a liquid crystal display (LCD) screen or any other appropriate display
- input devices 206 such as a keyboard and control buttons
- persistent memory 244 random access memory (RAM) 246, read only memory (ROM) 248, auxiliary input/output (I/O) subsystems 250
- data port 252 such as a conventional serial data port or a Universal Serial
- Display 204 can be realized as a touch-screen display in some embodiments.
- the touch-screen display can be constructed using a touch-sensitive input surface coupled to an electronic controller and which overlays the visible element of display 204.
- the touch-sensitive overlay and the electronic controller provide a touch-sensitive input device and processor 240 interacts with the touch-sensitive overlay via the electronic controller.
- Communication systems 211 includes one or more communication systems for communicating with wireless WAN 115 and wireless access points 125a and 125b within the wireless network.
- the particular design of communication systems 211 depends on the wireless network in which mobile device 130 is intended to operate. Mobile device 130 can send and receive communication signals over the wireless network after the required network registration or activation procedures have been completed.
- Processor 240 operates under stored program control and executes software modules 221 stored in memory such as persistent memory 244 or ROM 248.
- Processor 240 can execute code means or instructions.
- ROM 248 can contain data, program instructions or both.
- Persistent memory 244 can contain data, program instructions, or both.
- persistent memory 244 is rewritable under control of processor 240, and can be realized using any appropriate persistent memory technology, including EEPROM, EAROM, FLASH, and the like.
- software modules 221 can include operating system software 223. Additionally, software modules 221 can include software applications 225.
- persistent memory 244 stores user-profile information, including, one or more conference dial-in telephone numbers.
- Persistent memory 244 can additionally store identifiers related to particular conferences.
- Persistent memory 244 can also store information relating to various people, for example, name of a user, a user's identifier (user name, email address, or any other identifier), place of employment, work phone number, home address, etc.
- Persistent memory 244 can also store one or more speech audio files, one or more partial transcripts, one or more complete conference transcripts, a speech-to-text database, one or more voice templates, one or more translation applications, or any combination thereof. Each partial transcript has an associated date/time stamp, conference identifier, and speaker identifier.
- Speech-to-text database includes information that can be used by transcription system 300 to convert a speech audio file into text.
- the one or more voice templates can be used to provide voice recognition functionality to transcription system 300.
- the one or more translation applications can be used by transcription system 300 to create a transcript of a conference in a language that is different from a language spoken in the original audio recording of the conference.
- Software modules 221, for example, transcription system 300, or parts thereof can be temporarily loaded into volatile memory such as RAM 246.
- RAM 246 is used for storing runtime data variables and other types of data or information. In some embodiments, different assignment of functions to the types of memory could also be used.
- software modules 221 can include a speech-to-text module.
- the speech-to-text module can convert a speech audio file into text, translate speech into one or more languages, perform voice recognition, or some combination thereof.
- Software applications 225 can further include a range of applications, including, for example, an application related to transcription system 300, e-mail messaging application, address book, calendar application, notepad application, Internet browser application, voice communication (i.e., telephony) application, mapping application, or a media player application, or any combination thereof.
- Each of software applications 225 can include layout information defining the placement of particular fields and graphic elements (for example, text fields, input fields, icons, etc.) in the user interface (i.e., display 204) according to the application.
- auxiliary input/output (I/O) subsystems 250 comprise an external communication link or interface, for example, an Ethernet connection.
- auxiliary I/O subsystems 250 can further comprise one or more input devices, including a pointing or navigational tool such as a clickable trackball or scroll wheel or thumbwheel, or one or more output devices, including a mechanical transducer such as a vibrator for providing vibratory notifications in response to various events on mobile device 130 (for example, receipt of an electronic message or incoming phone call), or for other purposes such as haptic feedback (touch feedback).
- mobile device 130 also includes one or more removable memory modules 230 (typically comprising FLASH memory) and one or more memory module interfaces 232.
- removable memory module 230 is to store information used to identify or authenticate a user or the user's account to wireless network (for example WAN 115 and/or PLMN 120).
- wireless network for example WAN 115 and/or PLMN 120.
- SIM Subscriber Identity Module
- Memory module 230 is inserted in or coupled to memory module interface 232 of mobile device 130 in order to operate in conjunction with the wireless network.
- the speech-to-text functionality can be augmented via data stored on one or more memory modules 230.
- the memory modules can contain speech-to-text data specific to particular topics, like law, medicine, engineering, etc.
- transcription system 300 can use data on memory modules 130 to increase the accuracy of the speech-to-text conversion.
- one or more memory modules 130 can contain one or more translation databases specific to different languages, thus augmenting the capability of transcription system 300 in the speech-to-text conversion and potential translation of different languages into one language.
- the conference could take place in Chinese and English and transcription system can produce a single transcript in English.
- transcription system can produce multiple transcripts in different languages. For example, the Chinese speaker would receive a transcript in Chinese and the English speaker a transcript in English.
- speakers can receive all the transcripts produced. For example, both the English and the Chinese speaker would receive the Chinese and the English transcripts.
- one or more memory modules 130 can contain one or more voice templates that can be used by transcription system 300 for voice recognition.
- Mobile device 130 stores data 227 in persistent memory 244.
- data 227 includes service data comprising information required by mobile device 130 to establish and maintain communication with the wireless network (for example WAN 115 and/or PLMN 120).
- Data 227 can also include, for example, scheduling and connection information for connecting to a scheduled call.
- Data 227 can include transcription system data used by mobile device 130 for various tasks.
- Data 227 can include speech audio files generated by the user of mobile device 130 as the user participates in the conference. For example, if the user says "I believe that this project should be handled by Jill", transcription system 300 can record this statement in a speech audio file. The speech audio file has a particular date/time stamp, a conference identifier, and a speaker identifier.
- data 227 can include an audio recording of the entire conference.
- Data 227 can also include various types of transcripts. For example, types of transcripts can include partial, complete, audio, text, linked, or any combination thereof.
- Mobile device 130 also includes a battery 238 which furnishes energy for operating mobile device 130.
- Battery 238 can be coupled to the electrical circuitry of mobile device 130 through a battery interface 236, which can manage such functions as charging battery 238 from an external power source (not shown) and the distribution of energy to various loads within or coupled to mobile device 130.
- Short-range communication subsystem 262 is an additional optional component that provides for communication between mobile device 130 and different systems or devices, which need not necessarily be similar devices.
- short-range communication subsystem 262 can include an infrared device and associated circuits and components, or a wireless bus protocol compliant communication device such as a BLUETOOTH® communication module to provide for communication with similarly-enabled systems and devices.
- a predetermined set of applications that control basic device operations, including data and possibly voice communication applications can be installed on mobile device 130 during or after manufacture. Additional applications and/or upgrades to operating system software 223 or software applications 225 can also be loaded onto mobile device 130 through the wireless network (for example WAN 115 and/or PLMN 120), auxiliary I/O subsystem 250, data port 252, short-range communication subsystem 262, or other suitable subsystem such as 264.
- the downloaded programs or code modules can be permanently installed, for example, written into the program memory (for example persistent memory 244), or written into and executed from RAM 246 for execution by processor 240 at runtime.
- Mobile device 130 can provide three principal modes of communication: a data communication mode, a voice communication mode, and a video communication mode.
- a received data signal such as a text message, an e-mail message, Web page download, or an image file are processed by communication systems 211 and input to processor 240 for further processing.
- a downloaded Web page can be further processed by a browser application, or an e-mail message can be processed by an e-mail message messaging application and output to display 204.
- a user of mobile device 130 can also compose data items, such as e-mail messages, for example, using the input devices in conjunction with display 204. These composed items can be transmitted through communication systems 211 over the wireless network (for example WAN 115 and/or PLMN 120).
- mobile device 130 In the voice communication mode, mobile device 130 provides telephony functions and operates as a typical cellular phone. In the video communication mode, mobile device 130 provides video telephony functions and operates as a video teleconference term. In the video communication mode, mobile device 130 utilizes one or more cameras (not shown) to capture video of video teleconference.
- FIG. 3 is a block diagram depicting an example transcription system 300.
- transcription system 300 includes an interface module 310, a speech-to-text module 320, a communication module 330, a control module 340, and a data storage module 350. It is appreciated that one or more of these modules can be deleted, modified, or combined together with other modules.
- Figure 4 illustrates an example graphical user interface being displayed (for example via interface module 310) on the display of the mobile device.
- Menu 410 can be accessed from the desktop of a mobile device (for example, mobile device 130). In some embodiments, menu 410 can be accessed via an actual button on the mobile device. In some embodiments, menu 410 can be accessed when one or more applications are active. Menu 410 can contain a plurality of commands, including create transcription command 420, activate note taking command 430, and view conference transcript list command 440.
- Selecting create transcription command 420 triggers the execution of transcription system 300 (for example via interface module 310).
- Create transcription command 420 can be executed before, during, or after mobile device 130 participates in the conference call.
- the conference control can be an audio teleconference or a video teleconference.
- create transcription command 420 causes the transcription system 300 to automatically enter a mode of operation that creates speech audio files of anything the user of mobile device 130 says while mobile device is coupled to the conference.
- Transcription system 300 can start recording when it detects the user speaking and can cease recording when no speech is detected for a predetermined time. Transcription system 300 can then store the recorded speech as a speech audio file.
- Each speech audio file created has a date/time stamp, a conference identifier, and a speaker identifier.
- the date/time stamp provides the date and time when the speech audio file was created.
- the conference identifier associates the speech audio file to its corresponding conference.
- the speaker identifier associates the speech audio file with the speaker.
- the speaker identifier can be the name of a user, a user's identifier (user name, email address, or any other identifier), work phone number, etc.
- the created speech audio file also has an associated video component.
- the associated video component can be part of the speech audio file, or a separate video file corresponding to the speech audio file.
- Selecting activate note taking command 430 triggers the execution of transcription system 300 (for example via interface module 310).
- Note taking command 430 can be executed before or during mobile device 130's participation in the conference call.
- note taking command 430 causes transcription system 300 to automatically enter a mode of operation that creates speech audio files in response to specific key words said by the user. For example, if the user says "ACTION ITEM Jim's letter to counsel needs to be revised.” Transcription system 300 would then create a speech audio file containing a recording of the speech after the key words, "Jim's letter to counsel needs to be revised.”
- Key words can include, for example, "ACTION ITEM,” “CREATE TRANSCRIPT,” “OFF THE RECORD,” “END TRANSCRIPT,” etc.
- Each speech audio file created has a date/time stamp, a conference identifier, and a speaker identifier.
- the date/time stamp provides the date and time when the speech audio file was created.
- the conference identifier associates the speech audio file to its corresponding conference.
- the speaker identifier associates the speech audio file with the speaker.
- the speaker identifier can be the name of a user, a user's identifier (user name, email address, or any other identifier), work phone number, etc.
- the key word “ACTION ITEM” causes transcription system 300 to create a speech audio file of the user's statement immediately following the key words.
- the key words “CREATE TRANSCRIPT” allows the user to verbally activate create transcription command 420 during the conference.
- the key words “OFF THE RECORD” prevents transcription system 300 from including the user's statement immediately following "OFF THE RECORD” in the transcript, when create transcription 420 has been executed.
- the key words “END TRANSCRIPT” causes transcription system 300 to cease creating a transcript.
- Selecting view conference transcript list command 430 triggers the execution of transcription system 300 (for example via interface module 310).
- the view conference transcript list command 430 is not displayed unless there is at least one conference record stored in memory (for example, data storage module 350).
- View conference transcript list command 430 can be executed before, during, or after mobile device 130 participates in the conference call. Referring back to Figure 3 , when activated, view conference transcript list command 430 causes transcription system 300 to access interface module 310 and data storage module 350.
- Interface module 310 can display a list of previously transcribed conferences.
- interface module 310 enables the user to view one or more conference records.
- a conference record can include a partial or complete transcript.
- a transcript can include audio recordings of the conference, video recordings of the conference, textual representation of the conference, or some combination thereof.
- a partial transcript corresponds to transcribed statements made by a particular user during a particular conference.
- a partial transcript could be a statement from the mobile device user made during the conference.
- Each partial transcript created on a mobile device corresponds to statements made using transcription system 300 operating on that device. Accordingly, during the course of a conference, each participating mobile device can have a plurality of partial transcripts that are associated with the user of that device. When the plurality of partial transcripts from each device are collected and arranged in chronological order, a complete transcript is created.
- FIG. 5 illustrates an example conference transcript list graphical user interface (GUI) 500 generated by transcription system 300 (for example, by interface module 310), displaying a plurality of conference records 510,520, and 530.
- Conference records 510,520, and 530 can be sorted and grouped according to specific features of conference records 510, 520, and 530. For example, specific features can include the date the conference occurred, the time the conference occurred, the content of the conference, the type of transcript (for example, partial, complete, audio, text, etc.), or any combination thereof.
- conference records 510, 520, and 530 are grouped by date to form groups 540 and 550, and then displayed to the user.
- Conference records 510, 520, and 530 that occur on the same day can additionally be ordered by the time the conference occurred.
- each conference record 510, 520, and 530 can display one or more indicators associated with their specific features.
- An indicator can be text icon, an audio icon, or a video icon that is associated with an entry in a particular conference record. Additionally, in some embodiments the icons can cause the execution of associated files.
- Audio icon 560 is an indicator that is displayed when an audio speech file is available as part of the conference record.
- audio icon 560 is an executable, which when executed by the user, begins playback of the speech audio file associated with audio icon 560.
- a video icon (not shown) is an indicator that is displayed when the speech audio file has available video content or has an associated video file available as part of the conference record.
- the video icon is an executable, which when executed by the user, begins playback of video content associated with the speech audio file that is associated with the video icon.
- Conference records 510 and 520 contain linked partial transcripts, and a linked complete transcript, respectively.
- a linked transcript (partial or complete) has portions of the transcript mapped to corresponding speech audio files.
- the linked transcript (partial or complete) has portions of the transcript mapped to corresponding video content associated with the speech audio files. For example, if a portion of a linked transcript reads "the sky is blue," when a user selects the associated audio icon 560, transcription system 300 automatically plays back the speech audio file mapped to that portion of the linked transcript, or "the sky is blue.” This can be useful if an error occurred in the speech-to-text conversion creating, for example, a nonsensical comment in the linked transcript. The user can simply click on audio icon 560 and transcription system 300 automatically plays the associated speech audio file associated with the transcript, thus providing a backup to the user in the event of improper speech-to-text conversion.
- Text icon 562 is displayed when the complete or partial transcript is available as part of the conference record.
- conference record 510 corresponds to "Conf: 1" and contains two individual entries. Both individual entries contain linked partial transcripts and interface module 310 conveys this information to the user by displaying audio icon 560 and a corresponding text icon 562.
- conference record 530 does not display an audio icon 560, but does display a text icon 562.
- the transcript of the conference only contains text.
- transcription system 300 allows the user to delete the entire conference record or selectively delete portions thereof. For example, if the conference record includes a linked transcript, the user can delete a speech audio file but keep the associated text, or vice-versa. Additionally, in some embodiments, transcription system 300 is automatically configured to remove the speech audio files after a predetermined condition is met. Example conditions include reaching a data storage threshold, successful transcript creation, a predetermined amount of time has passed since the conference occurred, or any combination thereof. Additionally, in some embodiments, the user can configure the predetermined conditions.
- text icon 562 can contain a link that opens the stored transcript information. For example, in conference record 520 only "Transcript” is displayed in text icon 562. In this embodiment, when a user selects " Transcript” , transcription module 300 links to the corresponding conference record window as illustrated in Figure 6 .
- FIG. 6 illustrates an example conference record graphical user interface (GUI) 600.
- Interface module 310 displays conference record GUI 600 when text icon 562 is selected.
- conference record GUI 600 corresponds to conference record 520.
- the selection of text icon 562 associated with a particular conference record can open a conference record GUI 600 that corresponds to conference record 520.
- Conference record GUI 600 includes one or more individual transcriptions (610) that are arranged in the correct chronological order. Additionally, each individual entry contains an identifier 620 associated with the speaker of the individual transcription. In some embodiments identifier 620 can link to contact information of the speaker corresponding to identifier 620.
- Conference record 520 includes a complete linked transcript, accordingly, one or more of the individual entries can be mapped to their respective speech audio files.
- the presence of an associated speech audio file is indicated by the text of the individual entry being underlined. Such that a user can select the text causing the automatic execution of the associated speech data file. In some embodiments, the user can correct or update the text in case a transcription error occurred. In other embodiments not shown one or more audio icons can be displayed that when executed cause the automatic execution of the associated speech data file. In other embodiments not shown one or more video icons can be displayed that, when executed, cause the automatic execution of a video component associated with the speech data file.
- interface module 310 can be coupled to speech-to-text module 320, communication module 330, control module 340, and data storage module 350.
- Speech-to-text module 320 is configured to convert a received speech audio file into text to create a partial transcript. Speech-to-text module 320 also associates the date/time stamp, the conference identifier, and the speaker identifier corresponding to the received speech audio file with the newly created partial transcript. Speech-to-text module 320 can be located on each mobile device, one or more servers, or some combination thereof.
- speech-to-text module 320 additionally includes a voice recognition feature.
- the voice recognition feature can be useful when two or more parties are participating in the conference using the same mobile device.
- Speech-to-text module 320 can then identify the speaker of a received speech audio data file using one or more voice templates stored in data storage module 350. If speech-to-text module 320 identifies more than one speaker, the multiple speaker identifiers are associated with the partial transcript.
- the partial transcript is also further broken down into a plurality of partial transcripts that each contain only one speaker. For example, if the speech audio file, when played, says "Jack can you explain option B (voice 1).
- speech-to-text module 320 can create two partial transcripts, one with a speaker identifier corresponding to voice 1 and a separate partial transcript with a speaker identifier corresponding to voice 2.
- speech-to-text module 320 is able to convert and translate the received speech audio file into one or more different languages using portions of a speech-to-text database stored in data storage module 350. For example, if the received speech audio file is in Chinese, the speech-to-text module 320 can produce a partial transcript in English. Additionally, in some embodiments, speech-to-text module 320 can produce multiple partial transcripts in different languages (e.g., Chinese and English) from the received speech audio file.
- Communication module 330 is configured to join the mobile device with one or more mobile devices participating in the conference.
- the conference can be hosted on a variety of conference hosing systems.
- communication module 330 can join the mobile device to conference hosted using a mobile bridge, a PBX, a conference bridge, or any combination thereof.
- communication module 330 can transmit speech audio files, partial transcripts, complete transcripts, voice templates, portions or all of a speech-to-text database, or any combination thereof.
- Communication module 330 is configured to transmit data via enterprise network 105, PLMN 120, WAN 115, or some combination thereof, to one or more mobile devices (for example, mobile devices 130,135,136, and 140), a server (for example, SMP 165), digital phones (for example digital phone 160), one or more computers (for example computers 142 and 143), or some combination thereof. Additionally, in some embodiments communication module 330 establishes a peer-to-peer connection with one or more mobile devices to transmit speech audio files, partial or complete transcripts, partial or complete linked transcripts, or any combination thereof, to the one or more mobile devices. Communication module 330 can be coupled to interface module 310, speech-to-text module 320, control module 340, and data storage module 350.
- Control module 340 is configured to monitor the mobile device microphone for the user's speech in a conference. Control module 340 can be located on each mobile device, on one or more central servers, or some combination thereof. Control module 340 records any detected user speech in an individual speech audio file. Additionally, in video conferences, control module 340 can record a video signal using, for example, one or more cameras, and associate the video component with the corresponding speech audio file. Each speech audio file is date and time stamped and associated with the conference. The speech audio files can be stored in data storage module 350. In some embodiments, immediately after a speech audio file is created, it is passed to speech-to-text module 320 for conversion into a partial transcript. Control module 340 is configured to map received partial transcripts to their respective speech audio files to create a partial linked transcript.
- Control module 340 is configured to arrange one or more partial transcripts in chronological order using the date/time stamps of each partial transcript. Additionally, in some embodiments control module 340 is configured to acquire all of the partial transcripts of the conference participants and assemble them in chronological order to create a complete transcript. In some embodiments, control module 340 then distributes the complete transcript to one or more of the conference participants. In some embodiments, control module 340 for each participating mobile device can synchronize itself with a conference bridge 132 so that the date/time stamp across each is consistent. This allows control module 340 to assemble the multiple partial transcripts in chronological order. In some embodiments, control module 340 can assemble the multiple partial transcripts in chronological order based on the content in the partial transcripts.
- control module 340 assembles at a server each of the partial transcripts into a complete transcript and then distributes the complete transcript to individual mobile devices participating in the conference.
- control module 340 operating on the mobile device creates one or more partial transcripts associated with the user of the mobile device.
- Each mobile device participating in the conference can have its own control module 340 that similarly creates one or more partial transcripts associated with the users of those devices.
- the partial transcripts are then distributed among the mobile devices, where each mobile device adds its own partial transcripts, if any, to the received partial transcripts until a complete transcript is formed.
- the method of distribution of the one or more partial transcripts can be a serial. In a serial distribution the mobile devices sends its one or more partial transcripts to a second mobile device participating in the conference.
- This second mobile device then adds its partial transcripts, if any, to the received partial transcripts to create an augmented partial transcript.
- the augmented partial transcript is then sent to a third mobile device participating in the conference and the process is repeated, until a complete transcript is formed.
- a complete transcript is formed when it includes all of the partial transcripts from each mobile device participating in the conference.
- the mobile device can receive partial transcripts from each mobile device participating in the conference and use the received partial transcripts to form a complete transcript. The mobile device can then distribute the complete transcript to one or more mobile devices participating in the conference.
- control module 340 can calculate a transmission geometry that minimizes the number of transmissions between mobile devices to create a complete transcript.
- control module 340 can calculate a transmission geometry that minimizes the time to create a complete transcript.
- the control module 340 on the mobile device where the linked complete transcript is formed then distributes the linked complete transcript to one or more mobile devices that participated in the conference.
- Control module 340 can be coupled to interface module 310, speech-to-text module 320, communication module 330, and data storage module 350.
- Data storage module 350 can also include a database, one or more computer files in a directory structure, or any other appropriate data storage mechanism such as a memory. Additionally, in some embodiments, data storage module 350 stores user profile information, including, one or more conference dial in telephone numbers. Data storage module 350 can also store speech audio files (and any associated video component), partial transcripts, complete transcripts, speaker identifiers, conference identifiers, one or more voice templates, a speech-to-text database, translation database, or any combination thereof Additionally, data storage module 350 can store a language preference. The language preference can be useful when transcription system 300 is capable of creating partial transcripts in different languages. Data storage module 350 also stores information relating to various people, for example, name, place of employment, work phone number, home address, etc. In some example embodiments, data storage module 350 is distributed across one or more network servers. Data storage module 350 can communicate with interface module 310, speech-to-text module 320, communication module 330, and control module 340.
- modules 310, 320, 330, and 340 can be software programs stored in a RAM, a ROM, a PROM, a FPROM, or other dynamic storage devices, or persistent memory for storing information and instructions.
- FIG. 7 is a flowchart representing an example method transcribing conference data that utilizes a central server. While the flowchart discloses the following steps in a particular order, it is appreciated that at least some of the steps can be moved, modified, or deleted where appropriate.
- a mobile device joins a conference (audio, video, or some combination thereof).
- the mobile device is a moderator device.
- the moderator device is used by the moderator of the conference.
- a transcription system is activated.
- the transcription system can be activated via a menu command, a voice command, an actual button on the organizing device, or some combination thereof.
- the transcription system when activated, automatically creates speech audio files of any speech detected at the microphone of the mobile device while it participates in the conference. In other embodiments, when activated, the transcription system automatically creates speech audio files in response to specific key words said by the user. For example, if the user says "ACTION ITEM Jim's letter to counsel needs to be revised," the transcription system would then create a speech audio file containing a recording of "Jim's letter to counsel needs to be revised.” Key words can include, action item, create transcript, off the record, end transcript, etc. In some embodiments, if the conference is a video conference, the transcription system can also record a video component that is associated with the created speech audio files.
- the key words "action item” can cause the transcription system to create a speech audio file of the user's statement immediately following the key word.
- the key words “create transcript” cause the transcription system to automatically create speech audio files for any speech detected at the microphone of the mobile device while it participates in the conference.
- the transcription system detects the key words “off the record,” it does not record the user's statement immediately following "off the record.”
- the transcription system starts recording after it detects the user speaking and ceases recording after no speech is detected for a predetermined time, and stores the recorded speech, creating a speech audio file. Additionally, if the conference is a video conference, the transcription system can also record a video component that is associated with the created speech audio files. Each speech audio file is date/time stamped, contains a conference identifier, and contains a speaker identifier. Additionally, in some embodiments (not shown) transcription system performs the additional step of voice recognition on one or more speech audio files.
- the transcription system performs speech-to-text conversion on one or more speech audio files to create one or more partial transcripts.
- Each partial transcript has an associated date/time stamp, conference identifier, and speaker identifier from the corresponding speech audio data file.
- the speech-to-text conversion occurs contemporaneously and independent from speech-to-text conversion that can occur on other devices participating in the conference.
- transcription system converts and translates the received speech audio file(s) into one or more different languages. For example, if the received speech audio file is in Chinese, transcription system can produce a partial transcript in English where appropriate. Similarly, in some embodiments, transcription system produces multiple partial transcripts in different languages (e.g., Chinese and English) from the received speech audio file.
- the transcription system additionally, links the one or more partial transcripts with their corresponding speech audio file.
- transcription system provides one or more partial transcripts to a server (for example, SMP 165).
- a server for example, SMP 165.
- the transcription system also sends the associated speech audio files to the server.
- the transcription system also sends the associated video component of the speech audio files to the server.
- the transcription system terminates the transcription service. This occurs, for example, when the user terminates the transcription service with an audio command or terminates the voice conference connection.
- step 770 the mobile device acquires a complete transcript from the central server.
- Figure 8 is a flowchart representing an example method for assembling a complete transcript from one or more partial transcripts by a central server. While the flowchart discloses the following steps in a particular order, it is appreciated that at least some of the steps can be moved, modified, or deleted where appropriate.
- a transcription system operating on a server acquires one or more partial transcripts from a plurality of mobile devices participating in a conference. If the acquired transcripts are linked transcripts, the transcription system also acquires the speech audio files that correspond to the one or more partial transcripts. Each received partial transcript includes a date/time stamp, a conference identifier, and a speaker identifier. Additionally, in some embodiments, if the conference is a video conference and the acquired transcripts are linked transcripts, the transcription system also acquires the associated video component of the speech audio files that correspond to the one or more partial transcripts.
- step 820 the transcription system determines whether all partial transcripts have been collected from the mobile devices participating in the conference. If the transcription system determines that there are still some remaining partial transcripts to be collected, the system continues to acquire partial transcripts (step 810). If the transcription system determines that all the partial transcripts have been collected, it proceeds to step 830.
- the transcription system arranges the collected partial transcripts in chronological order to form a complete transcript.
- the transcription system first groups the partial transcripts by conference (not shown) using the conference identifiers of the received partial transcripts. Then using the date/time stamp of each partial transcript, with the correct conference group, arranges them in chronological order.
- the transcription system aggregates the plurality of partial transcripts into a single complete transcript. In some embodiments, at least some of the aggregated partial transcripts are linked partial transcripts, and are aggregated into a single complete linked conference.
- each participating mobile device synchronizes itself with a conference bridge so that the date/time stamp across each is consistent. This allows the transcription system to assemble the multiple partial transcripts in chronological order. In some embodiments, the transcription system assembles the multiple partial transcripts in chronological order based on the content in the partial transcripts.
- the transcription system performs the additional step of grouping the partial transcripts by language before arranging the partial transcripts in chronological order.
- step 840 the transcription system distributes the complete transcripts to one or more mobile devices participating in the conference.
- Figure 9 is a flowchart representing an example method transcribing conference data that shares transcript processing among conference devices. While the flowchart discloses the following steps in a particular order, it is appreciated that at least some of the steps can be moved, modified, or deleted where appropriate.
- a mobile device joins a conference.
- the mobile device is the conference moderator.
- a transcription system is activated.
- the transcription system can be activated via a menu command, a voice command, an actual button on the organizing device, or some combination thereof.
- transcription system when activated, automatically creates speech audio files of any speech detected at the microphone of the mobile device while it participates in the conference.
- the transcription system starts recording after it detects the user speaking and ceases recording after no speech is detected for a predetermined time, and stores the recorded speech, creating a speech audio file.
- Each speech audio file created has a date/time stamp, a conference identifier, and a speaker identifier.
- the date/time stamp provides the date and time when the speech audio file was created.
- the conference identifier associates the speech audio file to its corresponding conference.
- the speaker identifier associates the speech audio file with the speaker.
- the speaker identifier can be the name of a user, a user's identifier (user name, email address, or any other identifier), work phone number, etc.
- the transcription system also records a video component that corresponds to the created speech audio file.
- transcription system performs the additional step of voice recognition on one or more speech audio files. This can be useful when multiple parties are participating in the conference using the same device.
- the transcription system then associates a speaker identifier for each speaker.
- the transcription system performs speech-to-text conversion on one or more speech audio files to create one or more partial transcripts.
- Each partial transcript has an associated date/time stamp, conference identifier, and speaker identifier from the corresponding speech audio data file.
- the speech-to-text conversion occurs contemporaneously and independent from speech-to-text conversion that can occur on other devices participating in the conference.
- transcription system converts and translates the received speech audio file(s) into one or more different languages. For example, if the received speech audio file is in Chinese, the transcription system can produce a partial transcript in English where appropriate. Similarly, in some embodiments, the transcription system produces multiple partial transcripts in different languages (e.g., Chinese and English) from the received speech audio file.
- the transcription system links the one or more partial transcripts with their corresponding speech audio file.
- Each linked partial transcript has an associated date/time stamp, conference identifier, and speaker identifier.
- the transcription system links the one or more partial transcripts with the video component associated with the corresponding speech audio file
- step 925 the transcription system terminates the transcription service. This occurs, for example, when the user terminates the transcription service with an audio command or terminates the voice conference connection.
- the transcription system determines whether the mobile device is a designated device.
- the designated device can the moderator device, an organizing device, or any other device participating in the conference.
- the moderator device is the device acting as the conference moderator.
- the organizing device is the device that initially established the conference. If the mobile device is the designated device, the transcription system automatically calculates a transmission geometry that minimizes the number of transmissions between mobile devices to create a complete transcript. Additionally, the transcription system calculates a transmission geometry to minimize the time needed to create a complete transcript (step 935).
- the transcription system then forms distribution instructions based on the transmission geometry.
- the distribution instructions provide mobile device conference participants with instructions regarding where to send their partial transcripts.
- the transcription system sends the one or more partial transcripts resident on the designated device and the calculated distribution instructions to one or more mobile devices participating in the conference, in accordance with the distribution instructions.
- the mobile device also sends one or more speech audio files that correspond to the one or more partial transcripts.
- step 945 the designated device acquires a complete transcript from one of the mobile devices participating in the conference and in step 950 the process ends.
- the mobile device acquires one or more partial transcripts and distribution instructions from another mobile device participating in the conference (step 955).
- the mobile device also receives one or more speech audio files that correspond to the one or more partial transcripts.
- step 960 the transcription system incorporates the received one or more partial transcripts with any local partial transcripts generated by the mobile device during the conference.
- Step 960 includes comparing the conference identifiers of the received one or more partial transcripts to the conference identifiers of the local partial transcripts.
- the transcription system then groups the received one or more partial transcripts with any local partial transcripts containing the same conference identifier.
- the transcription system then orders the grouped partial transcripts in chronological order using the date/time stamps of the grouped partial transcripts.
- the transcription system determines whether the arranged one or more partial transcripts constitute a complete transcript.
- a complete transcript can be formed when all partial transcripts from each mobile device participating in the conference have been acquired. If all partial transcripts from mobile devices participating in the conference have been acquired, in a step not shown the transcription system automatically aggregates the plurality of partial transcripts into a single complete transcript. In some embodiments, at least some of the aggregated partial transcripts are linked partial transcripts, and are aggregated into a single complete linked conference. In some embodiments, the corresponding speech audio files are embedded in the linked complete transcript. If the conference is complete, in step 970 the transcription system transmits the complete transcript to one or more mobile devices that participated in the conference and the process ends (step 950).
- transcription system also sends one or more corresponding speech audio files.
- the speech audio files are embedded within the received transcript.
- the transcription system also sends the video component associated with the one or more corresponding speech audio files.
- step 975 transcription system sends the grouped and ordered partial transcripts and the received distribution instructions to one or more mobile devices participating in the conference, in accordance with the received distribution instructions.
- the mobile device also sends one or more speech audio files that correspond to the one or more partial transcripts.
- the mobile device acquires a complete transcript from one of the mobile devices participating in the conference, and the process then ends (step 950).
- transcription system also acquires one or more corresponding speech audio files.
- the speech audio files are embedded within the received transcript.
- the transcription system also acquires the video component associated with the one or more corresponding speech audio files.
- Embodiments of the present application are not limited to any particular operating system, mobile device architecture, server architecture, or computer programming language.
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Telephone Function (AREA)
Claims (15)
- Procédé de transcription de conférence téléphonique comprenant le fait :de joindre une conférence téléphonique audio avec un dispositif (130) associé à un participant d'une pluralité de participants joignant la conférence par l'intermédiaire d'un ou plusieurs dispositifs associés (135, 136, 140) ;de créer, au niveau du dispositif, un fichier audio vocal d'une partie de la conférence détectée par un microphone du dispositif recevant le son local du participant ;caractérisé par le fait :de convertir simultanément, au niveau du dispositif, le fichier audio vocal en une transcription partielle locale de la partie de la conférence détectée par le microphone ; etd'acquérir, au niveau du dispositif, une pluralité de transcriptions partielles à distance à partir d'au moins l'un des dispositifs associés, et de former une transcription complète ayant la transcription partielle locale et la pluralité de transcriptions partielles à distance.
- Procédé de la revendication 1, comprenant en outre le fait :de fournir la transcription partielle locale à au moins l'un des dispositifs associés.
- Procédé de la revendication 2, dans lequel la pluralité acquise de transcriptions partielles à distance sont combinées avec la transcription partielle locale pour constituer la transcription complète.
- Procédé de l'une des revendications 1 à 3, dans lequel la transcription partielle comporte un timbre horodateur associé et un identifiant de conférence.
- Procédé de la revendication 4, comprenant en outre le fait :de regrouper la pluralité acquise de transcriptions partielles à distance et la transcription partielle locale par identifiant de conférence ;de classer des transcriptions partielles regroupées par ordre chronologique en utilisant leurs timbres horodateurs ;d'agréger les transcriptions partielles classées en une transcription complète ; etde distribuer la transcription complète à au moins l'un des dispositifs associés.
- Procédé de l'une des revendications 1 à 5, comprenant en outre le fait :d'effectuer une identification vocale sur le fichier audio vocal.
- Procédé de l'une des revendications 1 à 6, dans lequel la transcription partielle locale est une transcription liée, et la transcription complète est une transcription liée.
- Support lisible par ordinateur non-transitoire comprenant un code de programme, le code de programme pouvant fonctionner, lorsqu'il est exécuté par un dispositif (130), pour amener le dispositif à effectuer un procédé, le procédé comprenant le fait :de joindre une conférence téléphonique audio avec le dispositif associé à un participant d'une pluralité de participants joignant la conférence par l'intermédiaire d'un ou plusieurs dispositifs associés (135, 136, 140) ;de créer un fichier audio vocal d'une partie de la conférence détectée par un microphone du dispositif recevant le son local du participant ;caractérisé par le fait :de convertir simultanément, au niveau du dispositif, le fichier audio vocal en une transcription partielle locale de la partie de la conférence détectée par le microphone ; etd'acquérir une pluralité de transcriptions partielles à distance à partir d'au moins l'un des dispositifs associés, et de former une transcription complète ayant la transcription partielle locale et la pluralité de transcriptions partielles à distance.
- Support lisible par ordinateur de la revendication 8, comprenant en outre le fait :de fournir la transcription partielle locale à au moins l'un des dispositifs associés.
- Support lisible par ordinateur de la revendication 9, dans lequel la pluralité acquise de transcriptions partielles à distance sont combinées avec la transcription partielle locale pour constituer la transcription complète.
- Support lisible par ordinateur de l'une des revendications 8 à 10, dans lequel la transcription partielle comporte un timbre horodateur associé et un identifiant de conférence.
- Support lisible par ordinateur de l'une des revendications 8 à 11, dans lequel le fichier audio vocal est dans une première langue, et la transcription partielle locale est dans une deuxième langue.
- Support lisible par ordinateur de l'une des revendications 8 à 12, dans lequel la transcription partielle locale est une transcription liée, et la transcription complète est une transcription liée.
- Support lisible par ordinateur de la revendication 13, dans lequel la transcription complète liée comporte une icône audio associée à une partie de la transcription complète liée et à un fichier audio vocal correspondant, de sorte que, lorsque l'icône audio est sélectionnée, le dispositif lit le fichier audio vocal correspondant.
- Dispositif (130) pour faciliter la création d'une transcription d'une conférence téléphonique audio, comprenant :un ou plusieurs processeurs (240) configurés pour exécuter des modules ; etune mémoire (244) stockant les modules, les modules comprenant :un module de communication (330) configuré pour joindre la conférence téléphonique audio, un participant étant l'un d'une pluralité de participants joignant la conférence par l'intermédiaire d'un ou plusieurs dispositifs associés (135, 136, 140) ;un module d'interface (310) configuré pour créer un fichier audio vocal d'une partie de la conférence détectée par un microphone du dispositif recevant le son local du participant ;caractérisé par :un module de conversion de parole en texte (320) configuré pour convertir simultanément, au niveau du dispositif, le fichier audio vocal en une transcription partielle locale de la partie de la conférence détectée par le microphone ; etun module de commande (340) configuré pour acquérir une pluralité de transcriptions partielles à distance à partir d'au moins l'un des dispositifs associés, et pour former une transcription complète ayant la transcription partielle locale et la pluralité de transcriptions partielles à distance.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP11179790.8A EP2566144B1 (fr) | 2011-09-01 | 2011-09-01 | Transcription de conférence de voix sur texte |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP11179790.8A EP2566144B1 (fr) | 2011-09-01 | 2011-09-01 | Transcription de conférence de voix sur texte |
Publications (3)
Publication Number | Publication Date |
---|---|
EP2566144A1 EP2566144A1 (fr) | 2013-03-06 |
EP2566144A9 EP2566144A9 (fr) | 2013-06-05 |
EP2566144B1 true EP2566144B1 (fr) | 2017-05-03 |
Family
ID=44773983
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP11179790.8A Active EP2566144B1 (fr) | 2011-09-01 | 2011-09-01 | Transcription de conférence de voix sur texte |
Country Status (1)
Country | Link |
---|---|
EP (1) | EP2566144B1 (fr) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20210350790A1 (en) * | 2020-05-06 | 2021-11-11 | Spotify Ab | Systems and methods for inferring the language of media content item |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10147415B2 (en) | 2017-02-02 | 2018-12-04 | Microsoft Technology Licensing, Llc | Artificially generated speech for a communication session |
CN111432157B (zh) * | 2020-02-18 | 2023-04-07 | 视联动力信息技术股份有限公司 | 基于视联网的会议处理方法、装置、设备及存储介质 |
CN111654658B (zh) * | 2020-06-17 | 2022-04-15 | 平安科技(深圳)有限公司 | 音视频通话的处理方法、系统、编解码器及存储装置 |
CN113011169B (zh) * | 2021-01-27 | 2022-11-11 | 北京字跳网络技术有限公司 | 一种会议纪要的处理方法、装置、设备及介质 |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6850609B1 (en) * | 1997-10-28 | 2005-02-01 | Verizon Services Corp. | Methods and apparatus for providing speech recording and speech transcription services |
US20070133437A1 (en) * | 2005-12-13 | 2007-06-14 | Wengrovitz Michael S | System and methods for enabling applications of who-is-speaking (WIS) signals |
US20090326939A1 (en) * | 2008-06-25 | 2009-12-31 | Embarq Holdings Company, Llc | System and method for transcribing and displaying speech during a telephone call |
-
2011
- 2011-09-01 EP EP11179790.8A patent/EP2566144B1/fr active Active
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20210350790A1 (en) * | 2020-05-06 | 2021-11-11 | Spotify Ab | Systems and methods for inferring the language of media content item |
Also Published As
Publication number | Publication date |
---|---|
EP2566144A1 (fr) | 2013-03-06 |
EP2566144A9 (fr) | 2013-06-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CA2784090C (fr) | Transcription ecrite d'un appel conference | |
US8868051B2 (en) | Method and user interface for facilitating conference calls | |
US9020119B2 (en) | Moderation control method for participants in a heterogeneous conference call | |
CA2771503C (fr) | Procede et appareil pour opter de se joindre a une teleconference | |
EP2501118B1 (fr) | Procédé et appareil pour identifier un appel en conférence à partir d'un enregistrement d'événements | |
US20130339455A1 (en) | Method and Apparatus for Identifying an Active Participant in a Conferencing Event | |
US8611877B2 (en) | Automatic management control of external resources | |
US10231075B2 (en) | Storage and use of substitute dial-in numbers for mobile conferencing application | |
CA2818776C (fr) | Methode et appareil pour identifier un participant actif dans une conference | |
EP2566144B1 (fr) | Transcription de conférence de voix sur texte | |
EP2587721B1 (fr) | Procédé de contrôle de la modération pour les participants à un appel de conférence hétérogène | |
EP2587778B1 (fr) | Contrôle de gestion automatique pour ressources externes | |
EP2675148B1 (fr) | Stockage et utilisation de numéros indicatifs de substitution pour application de conférence mobile | |
CA2793374C (fr) | Methode de controle de moderation pour les participants a un appel conference heterogene | |
CA2793522C (fr) | Commande de gestion automatique de ressources externes | |
CA2818636C (fr) | Stockage et utilisation de numeros indicatifs de remplacement pour une application de teleconference mobile |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
17P | Request for examination filed |
Effective date: 20110901 |
|
AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
AX | Request for extension of the european patent |
Extension state: BA ME |
|
RAP1 | Party data changed (applicant data changed or rights of an application transferred) |
Owner name: BLACKBERRY LIMITED |
|
RAP1 | Party data changed (applicant data changed or rights of an application transferred) |
Owner name: BLACKBERRY LIMITED |
|
17Q | First examination report despatched |
Effective date: 20140717 |
|
GRAP | Despatch of communication of intention to grant a patent |
Free format text: ORIGINAL CODE: EPIDOSNIGR1 |
|
INTG | Intention to grant announced |
Effective date: 20170109 |
|
GRAS | Grant fee paid |
Free format text: ORIGINAL CODE: EPIDOSNIGR3 |
|
GRAA | (expected) grant |
Free format text: ORIGINAL CODE: 0009210 |
|
AK | Designated contracting states |
Kind code of ref document: B1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
REG | Reference to a national code |
Ref country code: GB Ref legal event code: FG4D |
|
REG | Reference to a national code |
Ref country code: AT Ref legal event code: REF Ref document number: 891156 Country of ref document: AT Kind code of ref document: T Effective date: 20170515 Ref country code: CH Ref legal event code: EP |
|
REG | Reference to a national code |
Ref country code: IE Ref legal event code: FG4D |
|
REG | Reference to a national code |
Ref country code: DE Ref legal event code: R096 Ref document number: 602011037499 Country of ref document: DE |
|
REG | Reference to a national code |
Ref country code: NL Ref legal event code: FP |
|
REG | Reference to a national code |
Ref country code: AT Ref legal event code: MK05 Ref document number: 891156 Country of ref document: AT Kind code of ref document: T Effective date: 20170503 |
|
REG | Reference to a national code |
Ref country code: LT Ref legal event code: MG4D Ref country code: FR Ref legal event code: PLFP Year of fee payment: 7 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: NO Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20170803 Ref country code: FI Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20170503 Ref country code: LT Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20170503 Ref country code: AT Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20170503 Ref country code: GR Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20170804 Ref country code: HR Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20170503 Ref country code: ES Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20170503 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: BG Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20170803 Ref country code: IS Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20170903 Ref country code: SE Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20170503 Ref country code: LV Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20170503 Ref country code: PL Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20170503 Ref country code: RS Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20170503 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: CZ Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20170503 Ref country code: RO Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20170503 Ref country code: EE Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20170503 Ref country code: DK Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20170503 Ref country code: SK Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20170503 |
|
REG | Reference to a national code |
Ref country code: DE Ref legal event code: R097 Ref document number: 602011037499 Country of ref document: DE |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: SM Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20170503 Ref country code: IT Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20170503 |
|
PLBE | No opposition filed within time limit |
Free format text: ORIGINAL CODE: 0009261 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: NO OPPOSITION FILED WITHIN TIME LIMIT |
|
26N | No opposition filed |
Effective date: 20180206 |
|
REG | Reference to a national code |
Ref country code: CH Ref legal event code: PL |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: SI Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20170503 Ref country code: MC Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20170503 |
|
REG | Reference to a national code |
Ref country code: IE Ref legal event code: MM4A |
|
REG | Reference to a national code |
Ref country code: BE Ref legal event code: MM Effective date: 20170930 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: LU Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20170901 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: LI Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20170930 Ref country code: IE Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20170901 Ref country code: CH Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20170930 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: BE Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20170930 |
|
REG | Reference to a national code |
Ref country code: FR Ref legal event code: PLFP Year of fee payment: 8 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: MT Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20170901 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: HU Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT; INVALID AB INITIO Effective date: 20110901 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: CY Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20170503 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: MK Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20170503 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: TR Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20170503 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: PT Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20170503 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: AL Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20170503 |
|
PGFP | Annual fee paid to national office [announced via postgrant information from national office to epo] |
Ref country code: NL Payment date: 20230926 Year of fee payment: 13 Ref country code: GB Payment date: 20230927 Year of fee payment: 13 |
|
PGFP | Annual fee paid to national office [announced via postgrant information from national office to epo] |
Ref country code: FR Payment date: 20230925 Year of fee payment: 13 Ref country code: DE Payment date: 20230927 Year of fee payment: 13 |
|
REG | Reference to a national code |
Ref country code: DE Ref legal event code: R082 Ref document number: 602011037499 Country of ref document: DE Ref country code: DE Ref legal event code: R081 Ref document number: 602011037499 Country of ref document: DE Owner name: MALIKIE INNOVATIONS LTD., IE Free format text: FORMER OWNER: BLACKBERRY LIMITED, WATERLOO, ONTARIO, CA |
|
REG | Reference to a national code |
Ref country code: GB Ref legal event code: 732E Free format text: REGISTERED BETWEEN 20240620 AND 20240627 |